urlize.php

<?php #-*- coding: utf-8 -*-

/**
 * Format and translit a string like "The Fantastic ~'étonnante' permalink url" => "the-fantastic-etonnante-permalink-url"
 * 
 * @param string $string string to 
 * @param bool $dot_allowed allow dots (only one) chars in url
 * @return string 
 */
function urlize($string, $dot_allowed=false) {

    $dot = ($dot_allowed) ? '\.' : '';

    static $search, $replace;
  
    if (!$search) {
        $search = $replace = array();
        // Get the HTML entities table into an array
        $trans = get_html_translation_table(HTML_ENTITIES);
        // Go through the entity mappings one-by-one
        foreach ($trans as $literal => $entity) {
            // Make sure we don't process any other characters
            // such as fractions, quotes etc:
            if (ord($literal) >= 192) {
                // Get the accented form of the letter
                $search[] = utf8_encode($literal);
                // Get e.g. 'E' from the string '&Eacute'
                $replace[] = $entity[1];
            }
        }
    }
    $string = str_replace($search, $replace, $string);
    $string = strtolower($string);
    
    $find   = array(
      '/[^0-9a-z\-_'.$dot.']+/'      # blacklisted chars
      ,'/[-\.]+/'              # multi -, . or next to .
      
    );
    $repl   = array('-',($dot_allowed) ? '.' : '-');
    $string = trim($string,'-.');
    
    return  preg_replace($find, $repl, $string);
    
}